In this paper we present a model based method for fast face orientation estimation and pose recovery from a monocular image sequence captured by an uncalibrated camera. To accomplish this method, CANDIDE-3 model is used to construct 3D individual face model manually. Four facial feature points (outer corners of eyes and mouth) are tracked by SIFT algorithm. Taking advantage of these feature points and 3D individual face model, facial pose recovery can be quickly completed with a Fast Face Orientation Estimation Algorithm. An experimental system has been built to carry out the estimation method. The estimation results are robust and flexible.
Fast Face Orientation Estimation from an Uncalibrated Monocular Camera
2008 Congress on Image and Signal Processing ; 4 ; 186-190
01.05.2008
481084 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
3D Face pose estimation and tracking from a monocular camera
British Library Online Contents | 2002
|Recursive Estimation of Camera Motion from Uncalibrated Image Sequences
British Library Conference Proceedings | 1994
|Robust Position Estimation Using Images From an Uncalibrated Camera
British Library Conference Proceedings | 2003
|